Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12770
    Prev
    Next
    INDEX
    Explanations

    names of people or places involved in news or political events

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concess
    -0.65
    ipeg
    -0.65
     experience
    -0.64
    reth
    -0.62
     capacity
    -0.61
     overview
    -0.61
     prompt
    -0.60
     qual
    -0.59
    rid
    -0.58
     cog
    -0.58
    POSITIVE LOGITS
     aka
    1.07
    Jr
    0.91
     Sr
    0.90
     namely
    0.85
    ModLoader
    0.84
     Jr
    0.84
    Magikarp
    0.84
     although
    0.83
     albeit
    0.80
     whose
    0.79
    Activations Density 0.445%

    No Known Activations